The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...
Distance functions are an important component in many learning applications. However, the correct function is context dependent, therefore it is advantageous to learn a distance f...
Machine learning approaches to indoor WiFi localization involve an offline phase and an online phase. In the offline phase, data are collected from an environment to build a local...
Sinno Jialin Pan, Dou Shen, Qiang Yang, James T. K...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...